Triple

T15084020
Position Surface form Disambiguated ID Type / Status
Subject United States Census Bureau-designated Maine counties E360222 entity
Predicate dataPublishedIn P309 FINISHED
Object Census Bureau Gazetteer files
The Census Bureau Gazetteer files are official U.S. Census Bureau reference datasets that provide geographic names, locations, and related statistical information for places such as counties, cities, and other administrative areas.
 E1137089 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Census Bureau Gazetteer files | Statement: [United States Census Bureau-designated Maine counties, dataPublishedIn, Census Bureau Gazetteer files]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Census Bureau Gazetteer files
Context triple: [United States Census Bureau-designated Maine counties, dataPublishedIn, Census Bureau Gazetteer files]
  • A. MARC Geographic Areas
    MARC Geographic Areas is a standardized code list used in library cataloging to represent geographic locations in MARC records.
  • B. Geographic Names Information System
    The Geographic Names Information System is the official federal database of geographic feature names in the United States, providing standardized names and related information for use in maps and government publications.
  • C. GEOBASE
    GEOBASE is a bibliographic database specializing in worldwide research literature on geology, geography, earth sciences, ecology, and related environmental disciplines.
  • D. data.census.gov
    data.census.gov is the U.S. Census Bureau’s primary online platform for accessing and exploring official demographic, economic, and geographic data, including information on places in Michigan.
  • E. GNIS
    GNIS (Geographic Names Information System) is the official U.S. federal database that standardizes and catalogs geographic feature names across the United States.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Census Bureau Gazetteer files
Triple: [United States Census Bureau-designated Maine counties, dataPublishedIn, Census Bureau Gazetteer files]
Generated description
The Census Bureau Gazetteer files are official U.S. Census Bureau reference datasets that provide geographic names, locations, and related statistical information for places such as counties, cities, and other administrative areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Census Bureau Gazetteer files
Target entity description: The Census Bureau Gazetteer files are official U.S. Census Bureau reference datasets that provide geographic names, locations, and related statistical information for places such as counties, cities, and other administrative areas.
  • A. MARC Geographic Areas
    MARC Geographic Areas is a standardized code list used in library cataloging to represent geographic locations in MARC records.
  • B. Geographic Names Information System
    The Geographic Names Information System is the official federal database of geographic feature names in the United States, providing standardized names and related information for use in maps and government publications.
  • C. GEOBASE
    GEOBASE is a bibliographic database specializing in worldwide research literature on geology, geography, earth sciences, ecology, and related environmental disciplines.
  • D. data.census.gov
    data.census.gov is the U.S. Census Bureau’s primary online platform for accessing and exploring official demographic, economic, and geographic data, including information on places in Michigan.
  • E. GNIS
    GNIS (Geographic Names Information System) is the official U.S. federal database that standardizes and catalogs geographic feature names across the United States.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00275cfa88190a13fe20b585d9fcb completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae179a24819097019976707c93e1 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feb074bc9c8190a080bb57bb1844be completed May 9, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_69feb0c2af8081909e845bb8c9f9cdc7 completed May 9, 2026, 3:57 a.m.
Created at: April 10, 2026, 3:03 a.m.